Py学习  »  机器学习算法

深度学习推荐系统、CTR预估工业界实战论文整理分享

机器学习研究组订阅号 • 3 年前 • 323 次点击  

    本资源整理了深度学习在推荐系统、广告系统中应用的一些经典论文,涉及推荐系统中召回、排序、CTR预估、Embedding化、系统多样性、多目标,排序和混排的EE和RL等部分。

    资源整理自网络,源链接:https://github.com/imsheridan/DeepRec


目录

    点击率预估

    召回层

    排序层

    向量化

    多任务学习

    多样性

    探索/应用(EE)

    强化学习

    序列模型推荐

    用户模型

    BERT推荐模型

    图模型推荐(浅层/深层图模型)


点击率预估

    •[FiBiNET][RecSys 19][Weibo] FiBiNET_Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

    •[DSIN][IJCAI 19][Alibaba] Deep Session Interest Network for Click-Through Rate Prediction

    •[FGCNN][WWW 19][Huawei] Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction

    •[AutoInt][CIKM 19] AutoInt_Automatic Feature Interaction Learning via Self-Attentive Neural Networks

    •[DIEN][AAAI 19][Alibaba] Deep Interest Evolution Network for Click-Through Rate Prediction

    •[PNN][TOIS 18] Product-based Neural Networks for User Response Prediction

    •[xDeepFM][KDD 18][Microsoft] xDeepFM_Combining Explicit and Implicit Feature Interactions for Recommender Systems

    •[DCN][KDD 17][Google] Deep & Cross Network for Ad Click Predictions

    •[DIN][KDD 18][Alibaba] Deep Interest Network for Click-Through Rate Prediction

    •[FNN][ECIR 16] Deep Learning over Multi-field Categorical Data_A Case Study on User Response Prediction

    •[AFM][IJCAI 17] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks

    •[DeepFM][IJCAI 17][Huawei] DeepFM_A Factorization-Machine based Neural Network for CTR Prediction

    •[NFM][SIGIR 17] Neural Factorization Machines for Sparse Predictive Analytics

    •[WDL][DLRS 16][Google] Wide & Deep Learning for Recommender Systems

    

召回层

    •[JTM][NIPS 19] Joint Optimization of Tree-based Index and Deep Model for Recommender Systems

    •[MIND][arxiv 19][Alibaba] Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

    •[SDM][CIKM 19][Alibaba] Sequential Deep Matching Model for Online Large-scale Recommender System

    •[TDM][KDD 18][Alibaba] Learning Tree-based Deep Model for Recommender Systems

    •[NCF][WWW 17] Neural Collaborative Filtering

    •[YoutubeDNN][RecSys 16][Google] Deep Neural Networks for YouTube Recommendations

    •[DSSM][CIKM 13][Microsoft] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data

    

排序层

    •[PRM][RecSys 19][Alibaba] Personalized Re-ranking for Recommendation

    •[BERT4Rec][CIKM 19][Alibaba] BERT4Rec_Sequential Recommendation with Bidirectional Encoder Representations from Transformer

    •[BST][DLP-KDD 19][Alibaba] Behavior Sequence Transformer for E-commerce Recommendation in Alibaba

    

向量化

    •[Airbnb Embedding][KDD 18][Airbnb] Real-time Personalization using Embeddings for Search Ranking at Airbnb

    •[Alibaba Embedding][KDD 18][Alibaba] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba

    •[DeepWalk][KDD 14] DeepWalk- Online Learning of Social Representations

    •[LINE][WWW 15][Microsoft] LINE_Large-scale Information Network Embedding

    •[Node2vec][KDD 16] Node2vec_Scalable Feature Learning for Networks

    •[SDNE][KDD 16] Structural Deep Network Embedding

    •[Struc2Vec][KDD 17]struc2vec_Learning Node Representations from Structural Identity

    •[GraphSAGE][NIPS 17] Inductive Representation Learning on Large Graphs

    •[GCN][ICLR 17] Semi-supervised Classification with Graph Convolutional Networks

    

多任务学习

    •[RecSys 19][Alibaba] A Pareto-Efficient Algorithm for Multiple Objective Optimization in E-Commerce Recommendation

    •[MMoE][KDD 18][Google] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

    •[ESMM][SIGIR 18][Alibaba] Entire Space Multi-Task Model_An Effective Approach for Estimating Post-Click Conversion Rate

    

多样性

    •[CIKM 18][Google] Practical Diversified Recommendations on YouTube with Determinantal Point Processes

    •[NeurIPS 18][Hulu] Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity

    

探索/应用(EE)

    •[LinUCB][WWW 10][Yahoo] A Contextual-Bandit Approach to Personalized News Article Recommendation

    

强化学习

    •[IJCAI 19][Google] Reinforcement Learning for Slate-based Recommender Systems_A Tractable Decomposition and Practical Methodology

    •[WSDM 19][Google] Top-K Off-Policy Correction for a REINFORCE Recommender System

    •[DRN][WWW 18][Microsoft] DRN_A Deep Reinforcement Learning Framework for News Recommendation

    

序列模型推荐

    •[IJCAI 19] Sequential Recommender Systems_Challenges, Progress and Prospects

    

用户模型

    •[KDD 19][Tencent] A User-Centered Concept Mining System for Query and Document Understanding at Tencent

    

BERT推荐模型

    •[ALBERT][arxiv 19][Google] ALBERT_A Lite BERT for Self-supervised Learning of Language Representations

    •[BERT][arxiv 19][Google ]BERT_Pre-training of Deep Bidirectional Transformers for Language Understanding

    •[ERNIE][arxiv 19][Baidu] ERNIE_Enhanced Representation through Knowledge Integration

    •[T5][arxiv 19][Google] Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

    •[XLNet][arxiv 19][Google] XLNet_Generalized Autoregressive Pretraining for Language Understanding

    

图模型推荐

    浅层图向量化模型

    •[DeepWak][KDD 14] DeepWalk_Online Learning of Social Representations

    •[GraRep][CIKM 15] GraRep_Learning Graph Representations with Global Structural Information

    •[HOPE][KDD 16] Asymmetric Transitivity Preserving Graph Embedding

    •[LINE][WWW 15][Microsoft] LINE_Large-scale Information Network Embedding

    •[NetMF][WSDM 18] Network Embedding as Matrix Factorization_Unifying DeepWalk, LINE, PTE, and node2vec

    •[NetSMF][WWW 19] NetSMF_Large-Scale Network Embedding as Sparse Matrix

    •[Node2Vec][KDD 16] Node2Vec_Scalable Feature Learning for Networks

    •[ProNE][IJCAI 19] ProNE_Fast and Scalable Network Representation Learning

    •[SDNE][KDD 16] Structural Deep Network Embedding

    •[Struc2Vec][KDD 17] Struc2Vec_Learning Node Representations from Structural Identity

    

    图神经网络模型

    •[FastGCN][ICLR 18] FastGCN_Fast Learning with Graph Convolutional Networks via Importance Sampling

    •[GAT][ICLR 18] Graph Attention Networks

    •[GCN][ICLR 17] Semi-Supervised Classification with Graph Convolutional Networks

    •[GraphSAGE][NIPS 17] Inductive Representation Learning on Large Graphs


想要了解更多资讯,请扫描下方二维码,关注机器学习研究会

                                          


转自:深度学习与NLP

Python社区是高质量的Python/Django开发社区
本文地址:http://www.python88.com/topic/100795
 
323 次点击